© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54431
    Prev
    Next
    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ನಲ್ಲಿ
    -0.09
     sung
    -0.08
     ಆಗ
    -0.08
     cork
    -0.07
     cq
    -0.07
     whoever
    -0.07
    ไว
    -0.07
    .cont
    -0.07
    .cor
    -0.07
     klok
    -0.07
    POSITIVE LOGITS
     ranges
    0.08
    hetical
    0.08
    ieuze
    0.08
    umerator
    0.07
    ის
    0.07
    _ranges
    0.07
     azi
    0.07
    ranges
    0.07
    añas
    0.07
     company's
    0.07
    Activations Density 0.000%

    No Known Activations